Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Performance evaluation of GANs in a semisupervised OCR use case

Florian Wilhelm (inovex GmbH)
13:45–14:25 Thursday, 11 October 2018
Implementing AI, Models and Methods
Location: Windsor Suite
Secondary topics:  Computer Vision, Deep Learning models, Retail and e-commerce
Average rating: *****
(5.00, 1 rating)

Who is this presentation for?

  • Data scientists and practitioners

Prerequisite knowledge

  • A basic understanding of neural networks, deep learning, and image recognition

What you'll learn

  • Understand how semisupervised learning with GANs works
  • Explore beneficial semisupervised methods based on GANs for use cases with a limited amount of labeled data
  • Gain insight into an interesting OCR use case of an online vehicle marketplace


Online vehicle marketplaces are embracing artificial intelligence to ease the process of selling a vehicle on their platform. The tedious work of copying information from the vehicle registration document into some web form can be automated with the help of smart text-spotting systems, in which the seller takes a picture of the document, and the necessary information is extracted automatically.

Florian Wilhelm details the components of a text-spotting system, including the subtasks of object detection and optical character recognition (OCR). Florian elaborates on the challenges of OCR in documents with various distortions and artifacts, which rule out off-the-shelf products for this task. After offering an overview of semisupervised learning based on generative adversarial networks (GANs), Florian evaluates the performance gains of this method compared to supervised learning. More specifically, for a varying amount of labeled data, he compares the accuracy of a convolution neural network (CNN) to a GAN that uses additional unlabeled data during the training phase, showing that GANs significantly outperform classical CNNs in use cases with a lack of labeled data.

Photo of Florian Wilhelm

Florian Wilhelm

inovex GmbH

Florian Wilhelm is a data scientist at inovex in Cologne, Germany, where he focuses on recommender systems, mathematical modelling, and bringing data science to production. Previously, he worked at Blue Yonder, the leading platform provider for predictive applications and big data in the European market, and held a postdoctoral position at the Karlsruhe Institute of Technology. Florian’s background is in mathematics. He has more than five years of project experience in the field of predictive and prescriptive analytics and big data, as well as the domains of mathematical modelling, statistics, machine learning, high-performance computing and data mining. For the past few years, he has programmed mostly with the Python data science stack (NumPy, SciPy, scikit-learn, pandas, Matplotlib, Jupyter, etc.), to which he’s also contributed several extensions.